{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4VUCNUABUG4JFJWYL3UVARBK7U","short_pith_number":"pith:4VUCNUAB","canonical_record":{"source":{"id":"2505.04531","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T16:04:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3515b842d1486890d397b35699dbcb98dd27498d16995578058173670f1a4661","abstract_canon_sha256":"7b1245c8ec5d71a28321bd170d1deb92dbe8edcc3be40cf67c73287faf016469"},"schema_version":"1.0"},"canonical_sha256":"e56826d001a1b892a6d85ee950442afd13859c01441ffee3605bfcd8c605bb6e","source":{"kind":"arxiv","id":"2505.04531","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04531","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04531v2","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04531","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"4VUCNUABUG4J","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"4VUCNUABUG4JFJWY","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"4VUCNUAB","created_at":"2026-07-05T11:33:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4VUCNUABUG4JFJWYL3UVARBK7U","target":"record","payload":{"canonical_record":{"source":{"id":"2505.04531","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T16:04:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3515b842d1486890d397b35699dbcb98dd27498d16995578058173670f1a4661","abstract_canon_sha256":"7b1245c8ec5d71a28321bd170d1deb92dbe8edcc3be40cf67c73287faf016469"},"schema_version":"1.0"},"canonical_sha256":"e56826d001a1b892a6d85ee950442afd13859c01441ffee3605bfcd8c605bb6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:23.416501Z","signature_b64":"iRRx2JxE3qYFCGgMOMUAZQ1kmFatzT2GWCIkzEmjpF8XWJqp1Da6e4JDhyVlQ6Cd+u9haHTaRDn+26eyvEFZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56826d001a1b892a6d85ee950442afd13859c01441ffee3605bfcd8c605bb6e","last_reissued_at":"2026-07-05T11:33:23.416022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:23.416022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.04531","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sna4KzfHLUZHDizBYP687/zdOyY348lNF/tZX8g2jGY4sfu4Fyb+2lgozEG90ZcF+PD8npj62Ic22j89qnFBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:56:33.991587Z"},"content_sha256":"533e9b6a4b4ae2de373167474097502d3ba392a5e5751c12ae370365e2d7d578","schema_version":"1.0","event_id":"sha256:533e9b6a4b4ae2de373167474097502d3ba392a5e5751c12ae370365e2d7d578"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4VUCNUABUG4JFJWYL3UVARBK7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Josh McGiff, Nikola S. Nikolov","submitted_at":"2025-05-07T16:04:45Z","abstract_excerpt":"Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potential in productivity and communication, they overwhelmingly cater to high-resource languages like English. This has amplified concerns over linguistic inequality in natural language processing (NLP). This paper presents the first systematic review focused specifically on strategies to address data scarcity in generative language modelling for low-resource languages (LRL). Drawing from 54 studies, we identify, categoris"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04531","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.04531/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/NBK61MN70JV1JUr7wuVhSDlSMxPbVuszmCYRTQ8mxRr61agkQfNTW9GMxAWbLRe0DUsQHPlSFNK9CjdnzOfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:56:33.992086Z"},"content_sha256":"4924660e88dd61e0520d1f6a0ef9da0e9070332b2b86b93f49c7c3bdfd3b3d52","schema_version":"1.0","event_id":"sha256:4924660e88dd61e0520d1f6a0ef9da0e9070332b2b86b93f49c7c3bdfd3b3d52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VUCNUABUG4JFJWYL3UVARBK7U/bundle.json","state_url":"https://pith.science/pith/4VUCNUABUG4JFJWYL3UVARBK7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VUCNUABUG4JFJWYL3UVARBK7U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T13:56:33Z","links":{"resolver":"https://pith.science/pith/4VUCNUABUG4JFJWYL3UVARBK7U","bundle":"https://pith.science/pith/4VUCNUABUG4JFJWYL3UVARBK7U/bundle.json","state":"https://pith.science/pith/4VUCNUABUG4JFJWYL3UVARBK7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VUCNUABUG4JFJWYL3UVARBK7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4VUCNUABUG4JFJWYL3UVARBK7U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b1245c8ec5d71a28321bd170d1deb92dbe8edcc3be40cf67c73287faf016469","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T16:04:45Z","title_canon_sha256":"3515b842d1486890d397b35699dbcb98dd27498d16995578058173670f1a4661"},"schema_version":"1.0","source":{"id":"2505.04531","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04531","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04531v2","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04531","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"4VUCNUABUG4J","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"4VUCNUABUG4JFJWY","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"4VUCNUAB","created_at":"2026-07-05T11:33:23Z"}],"graph_snapshots":[{"event_id":"sha256:4924660e88dd61e0520d1f6a0ef9da0e9070332b2b86b93f49c7c3bdfd3b3d52","target":"graph","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.04531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potential in productivity and communication, they overwhelmingly cater to high-resource languages like English. This has amplified concerns over linguistic inequality in natural language processing (NLP). This paper presents the first systematic review focused specifically on strategies to address data scarcity in generative language modelling for low-resource languages (LRL). Drawing from 54 studies, we identify, categoris","authors_text":"Josh McGiff, Nikola S. Nikolov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T16:04:45Z","title":"Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04531","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:533e9b6a4b4ae2de373167474097502d3ba392a5e5751c12ae370365e2d7d578","target":"record","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b1245c8ec5d71a28321bd170d1deb92dbe8edcc3be40cf67c73287faf016469","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T16:04:45Z","title_canon_sha256":"3515b842d1486890d397b35699dbcb98dd27498d16995578058173670f1a4661"},"schema_version":"1.0","source":{"id":"2505.04531","kind":"arxiv","version":2}},"canonical_sha256":"e56826d001a1b892a6d85ee950442afd13859c01441ffee3605bfcd8c605bb6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56826d001a1b892a6d85ee950442afd13859c01441ffee3605bfcd8c605bb6e","first_computed_at":"2026-07-05T11:33:23.416022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:23.416022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iRRx2JxE3qYFCGgMOMUAZQ1kmFatzT2GWCIkzEmjpF8XWJqp1Da6e4JDhyVlQ6Cd+u9haHTaRDn+26eyvEFZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:23.416501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04531","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:533e9b6a4b4ae2de373167474097502d3ba392a5e5751c12ae370365e2d7d578","sha256:4924660e88dd61e0520d1f6a0ef9da0e9070332b2b86b93f49c7c3bdfd3b3d52"],"state_sha256":"24c42aa3d2eddbb6e5f1b5eec38dc1326ab613edbaab440f41cda5db7dd7622c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0gqli58iZintueDNN7sZc6jyKy2D3QPbLLocPN5MjHEUGvhnzOFHb4v29YK9aXSDakwDa5BiVSje7/2P2OSlCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:56:33.995553Z","bundle_sha256":"3d7e1b213bda1b6dde6640735474851b6aae7026596754c6417e459a306104cc"}}